Gaussian function
PulseAugur coverage of Gaussian function — every cluster mentioning Gaussian function across labs, papers, and developer communities, ranked by signal.
17 day(s) with sentiment data
-
Neural network concept dimension measurement questioned in new paper
A new paper explores the concept of "concept dimension" in neural representations, questioning common methods of measurement. Researchers demonstrate that iterative erasure counts, often used to quantify how many direct…
-
DP-SGD faces fundamental privacy-utility trade-off limitations
A new research paper published on arXiv details fundamental limitations in Differentially Private Stochastic Gradient Descent (DP-SGD), a common method for private model training. The study, analyzing DP-SGD under the $…
-
New research tackles multimodal sentiment and emotion analysis with advanced fusion techniques
Two new research papers explore advanced techniques for multimodal sentiment and emotion analysis. The first paper introduces MIDAS, a framework designed to handle incomplete or corrupted multimodal data by disentanglin…
-
New Fed-SRC method offers private, accurate RAG certification
Researchers have developed Fed-SRC, a novel certification method for federated retrieval-augmented generation (RAG) systems that ensures privacy and accuracy. This system allows clients to share only differentially priv…
-
New ML framework enhances drug discovery screening metrics
Researchers have developed a new machine learning framework to improve performance metric estimation in high-throughput screening (HTS) assays, which are crucial for early-stage drug discovery. The framework addresses t…
-
UniJEPA unifies image and video visual world modeling
Researchers have introduced UniJEPA, a novel unified architecture for self-supervised visual world modeling. This new framework integrates both image-level photometric prediction and video-level temporal prediction into…
-
New DeepFreqMark framework embeds watermarks in AI images
Researchers have developed DeepFreqMark, a novel framework for embedding watermarks into AI-generated images from Latent Diffusion Models (LDMs). Unlike previous methods that used fixed patterns, DeepFreqMark employs a …
-
New framework makes VARMA models practical for high-dimensional data
Researchers have developed a new framework for estimating Vector Autoregressive Moving-Average (VARMA) models, which were previously considered computationally impractical for high-dimensional data. This new method allo…
-
New splat-based method reduces metal artifacts in CT scans
Researchers have developed a novel splat-based framework for reducing metal artifacts in cone-beam CT scans. This method incorporates a physically grounded polychromatic forward model within a continuous Gaussian repres…
-
New framework tackles pose sensitivity in splat-based CT reconstruction
Researchers have developed a new framework to address pose sensitivity issues in splat-based computed tomography, particularly for sparse-view reconstruction. This method jointly refines geometric parameters during the …
-
New random features method approximates Grassmannian kernels efficiently
Researchers have developed a new method for approximating Grassmannian kernels using random feature maps. This approach addresses the computational and memory limitations of traditional methods when dealing with large, …
-
New bounds established for ReLU NTK Gram matrices
Researchers have established tight worst-case bounds for the smallest eigenvalue of ReLU neural tangent kernel (NTK) Gram matrices. The study focuses on unit vectors in a d-dimensional space, averaging pairwise gated in…
-
Two new papers explore theoretical underpinnings of score-based generative models
Two new arXiv papers explore score-based generative models from different theoretical angles. The first paper introduces Score Anisotropy Directions (SADs) to analyze network architecture's influence on model biases and…
-
Online learning refines wind tunnel airflow for enhanced robot flight
Researchers have developed an online learning algorithm to precisely control airflow in a vertical wind tunnel for testing advanced aerial robots. This method combines a simplified physical model with iterative learning…
-
New research characterizes log-likelihood ratio statistics in logistic regression
Researchers have characterized the finite sample behavior of the log-likelihood ratio statistic in binary logistic regression. Their findings provide a non-asymptotic analogue to the Wilks $\chi^2_d$ phenomenon, applica…
-
New framework maps stochastic programs to thermodynamic hardware for energy-efficient sampling
Researchers have developed a framework called "thermalizers" to map general stochastic programs onto thermodynamic hardware for energy-efficient sampling. This framework compiles factors of a stochastic program, represe…
-
Caliber defense mitigates AI model extraction via output perturbation
Researchers have developed Caliber, a novel defense mechanism against model extraction attacks on score-returning APIs. Caliber works by adding Gaussian noise to internal logits, which degrades the supervision signal us…
-
New c-rectified flow framework promises optimal transport for image generation
A new paper introduces "c-rectified flow," a cost-aware framework for large-scale image generation that offers computational and statistical guarantees. This method, designed to improve upon existing rectified flow tech…
-
New analytic planning method tackles uncertainty in reinforcement learning
Researchers have developed a new method for analytic planning under uncertainty in model-based reinforcement learning. This approach uses a compatibility principle between predictive transition distributions and value f…
-
Gaussian Perturbations Prevent Oversmoothing in Recurrent GNNs
Researchers have developed a novel method using persistent Gaussian perturbations to combat oversmoothing in recurrent graph neural networks (GNNs). This technique injects independent Gaussian noise after each propagati…